job-search

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The workflow explicitly directs the agent to call external public APIs (e.g., Fiber /v1/job-search and /v1/people-search, brand-dev /v1/brand/retrieve for domains, and hunter /v2/email-finder) that ingest and return untrusted public/job/people content which the agent is expected to read and use to drive follow-up actions like outreach and candidate selection, creating a clear avenue for indirect prompt injection.